Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Laguna XS 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: Laguna XS 2.1 (MoE) at FP16 · 66.9 GB weights · 265–397 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Arena Text Overall · style-controlled
UnratedNo exact matchNo reviewed exact Arena match
No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.
Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh
Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986
- Total memory at 4K context
- 68.0 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 265–397 tok/s
- Estimated first token
- ~0.1s
Every quantization on this machine
On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 12.2 GB | 13.2 GB | 339–509 tok/s | Runs great |
| Q3_K_M | 15.6 GB | 16.6 GB | 333–500 tok/s | Runs great |
| Q4_K_M | 20.6 GB | 21.6 GB | 325–488 tok/s | Runs great |
| Q5_K_M | 24.0 GB | 25.0 GB | 320–479 tok/s | Runs great |
| Q6_K | 29.0 GB | 30.1 GB | 312–468 tok/s | Runs great |
| Q8_0 | 35.6 GB | 36.6 GB | 303–454 tok/s | Runs great |
| FP16 | 66.9 GB | 68.0 GB | 265–397 tok/s | Runs great |
Ran Laguna XS 2.1 (MoE) on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →